Developer tools
Linear for AI agents.
Managed auth, ready-made tools.
Create and update issues, and read projects and cycles in your users' Linear teams.
Tools
What your agent can do in Linear.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own Linear connection.
-
Search issues
Readlinear_search_issuesFind issues by text, team or state.
-
Create an issue
Writelinear_create_issueCreate an issue in a team.
-
Update an issue
Writelinear_update_issueChange state, assignee or priority.
No tool matches that search.
Get started
Connect Linear
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect Linear
Each end user authorizes their own Linear account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own Linear account, once. const connection = await agent200 .user("user_123") .connect("linear"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the Linear tools
Name the user, the model and the tools. The model decides which Linear tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Find what I need in Linear.", tools: ["linear"], }); console.log(result.output);
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the Linear connector and how to use it.
Connector: Linear, through Agent200. In code: "linear". What it does: Create and update issues, and read projects and cycles in your users' Linear teams. Page: https://www.agent200.com/tools/linear/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on Linear's own page, through the authorization link Agent200 returns. Never ask a user for a Linear password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: linear_search_issues. Write tools: linear_create_issue, linear_update_issue. Name "linear" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/tools/linear/framework/claude/ https://www.agent200.com/tools/linear/framework/chatgpt/ https://www.agent200.com/tools/linear/framework/claude-code/ https://www.agent200.com/tools/linear/framework/muse/ https://www.agent200.com/tools/linear/framework/grok-bot/ https://www.agent200.com/tools/linear/framework/openai-dots/ https://www.agent200.com/tools/linear/framework/claude-duet/ https://www.agent200.com/tools/linear/framework/hermes-agent/ https://www.agent200.com/tools/linear/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /tools/linear.md
Guides
Use Linear with the AI you build on.
Step-by-step setup for Linear with a specific model, assistant or agent framework.
-
Linear + Claude
How to connect Linear to Claude
-
Linear + ChatGPT
How to connect Linear to ChatGPT
-
Linear + Claude Code
How to connect Linear to Claude Code
-
Linear + Muse
How to connect Linear to Muse
-
Linear + Grok Bot
How to connect Linear to Grok Bot
-
Linear + OpenAI Dots
How to connect Linear to OpenAI Dots
-
Linear + Claude Duet
How to connect Linear to Claude Duet
-
Linear + Hermes Agent
How to connect Linear to Hermes Agent
-
Linear + OpenClaw
How to connect Linear to OpenClaw
FAQ
Linear and Agent200, answered.
Who handles the Linear OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Linear.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Linear connection, never another user's. It cannot reach anything the user or Linear has not authorized.
Can I limit what my agent can do in Linear?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.